Feature based watermarking using watermark template match

This paper presents a robust digital image watermarking scheme using feature point detection and watermark template match. A scale interactive model based filter is used to extract the feature points of original image, based on which a watermark template is constructed and embedded adaptively into the local region of these points. Watermark decision is made by computing the statistical correlation between the watermark and the embedded region. Because the proposed feature detection is robust against JPEG compression, filtering, noise addition and geometric distortions, the proposed watermarking scheme can achieve good performance against these attacks, and experimental results also demonstrate the superiority.